Content generation using target content derived modeling and unsupervised language modeling

Active Publication Date: 2021-09-02
INK CONTENT INC
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

[0006]The foregoing has outlined some of the more pertinent features of the subject matter. These features should be construed to be merely illustrative. Many

Problems solved by technology

While these techniques and technologies provide a

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Content generation using target content derived modeling and unsupervised language modeling
  • Content generation using target content derived modeling and unsupervised language modeling
  • Content generation using target content derived modeling and unsupervised language modeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019]By way of background, FIG. 1 depicts an embodiment of a content editing technique according to this disclosure. In a typical but non-limiting client-server based implementation, a user is creating and inputting text into an editor, and that editor is executing as a client computer on the user's computing machine (a personal computer, laptop, tablet, other mobile device, Internet-of-Things (IoT) device, etc.). Typically, an editor is implemented as a client application, as a webpage (e.g., having form fields), or the like, and it provides a graphical user interface (GUI) by which a user can enter and edit text, all in a known manner. A back-end of the editing application executes in or in association with a server computing machine infrastructure, e.g., operating in a network-accessible location (e.g., a web server, a cloud infrastructure, or the like). The client computer displays (renders) the editor. As the user composes a document, he or she enters text in the editor and, a...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

Content generation leverages an unsupervised, generative pre-trained language model (e.g., a generative-AI). In this approach, a model derived by applying to given content relevant competitive content and one or more optimization targets is received. Based on optimization criteria encoded as embedding signals in the model, a determination is made regarding whether a template suitable for use as an input to the generative-AI exists in a set of templates. If so, the model embedding signals are merged into the template, or the template itself is transformed using the embedding signals, in either case creating a modified template. If, however, no template suitable as the input exists, the model and other information are input to a natural language processor to generate a generative-AI input. Either the modified template or the generative-AI input, as the case may be, is then applied through the generative-AI to generate an output competitively-optimized with respect to the optimization targets.

Description

BACKGROUNDTechnical Field[0001]This application relates generally to AI-assisted techniques for content generation.Brief Description of the Related Art[0002]It is known in the prior art to provide network-accessible (e.g., web-based) editing applications that automatically detect grammar, spelling, punctuation, word choice, and style errors in writing text being composed by a user in an online text editor. One commercial solution of this type works using a browser-based extension that identifies and enables a user to correct writing errors as the user enters text, e.g., on Google® Gmail, Facebook®, Twitter®, etc., in a web page or form. While these techniques and technologies provide advantages, they suffer from various deficiencies.[0003]State-of-the-art Artificial Intelligence (AI) techniques have recently begun to leverage unsupervised, generative pre-trained language models. The most well-known of this type is Generative Pre-trained Transformer 3 (GPT-3), which is an autoregress...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F40/30G06N5/04G06F16/9538G06F40/143
CPCG06F40/30G06N5/04G06N20/00G06F40/143G06F16/9538G06F40/134G06F40/232G06F40/253G06N5/022G06F16/908G06F16/9038G06F16/907G06N5/02
Inventor DE RIDDER, ALEXANDER
Owner INK CONTENT INC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products